[R] Why does qt() return Inf with certain negative ncp values?

[Bert Gunter]

Well, this will likely require close numerical analysis of the algorithm
used for the calculation, which I can't help with, but I do note for the
first case (I didn't bother checking the second) it may be useful to note
that besides returning Inf, I also got with -7 as ncp:

"There were 50 or more warnings"
all of which were:
"In qt(1 - 1 * (10^(-11)), 35, -7) :
  full precision may not have been achieved in 'pnt{final}' "

I got this warning for all the other values of ncp also.

So it looks like: Congratulations, you seem to have defeated the algorithm.

Bert Gunter

"The trouble with having an open mind is that people keep coming along and
sticking things into it."
-- Opus (aka Berkeley Breathed in his "Bloom County" comic strip )


On Mon, Jun 13, 2022 at 6:14 PM Stephen Berman <stephen.berman using gmx.net>
wrote:

> Can anyone explain why Inf appears in the following results?
>
> > sapply(-1:-10, \(ncp) qt(1-1*(10^(-4+ncp)), 35, ncp))
>  [1]  3.6527153  3.0627759  2.4158355  1.7380812  1.0506904  0.3700821
>  [7]        Inf -0.9279783 -1.5341759 -2.1085213
>
> > sapply(seq(-6.9, -7.9, -0.1), \(ncp) qt(1-1*(10^(-4+ncp)), 35, ncp))
>  [1] -0.2268386        Inf        Inf        Inf -0.4857400 -0.5497784
>  [7] -0.6135402 -0.6770143 -0.7401974 -0.8030853 -0.8656810
>
> In case it matters:
>
> > sessionInfo()
> R Under development (unstable) (2022-06-05 r82452)
> Platform: x86_64-pc-linux-gnu (64-bit)
> Running under: Linux From Scratch r11.0-165
>
> Matrix products: default
> BLAS:   /usr/lib/R/lib/libRblas.so
> LAPACK: /usr/lib/R/lib/libRlapack.so
>
> locale:
>  [1] LC_CTYPE=en_US.UTF-8       LC_NUMERIC=C
>  [3] LC_TIME=en_US.UTF-8        LC_COLLATE=en_US.UTF-8
>  [5] LC_MONETARY=en_US.UTF-8    LC_MESSAGES=en_US.UTF-8
>  [7] LC_PAPER=en_US.UTF-8       LC_NAME=C
>  [9] LC_ADDRESS=C               LC_TELEPHONE=C
> [11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C
>
> attached base packages:
> [1] stats     graphics  grDevices utils     datasets  methods   base
>
> loaded via a namespace (and not attached):
> [1] compiler_4.3.0 tools_4.3.0
>
> Thanks.
> Steve Berman
>
> ______________________________________________
> R-help using r-project.org mailing list -- To UNSUBSCRIBE and more, see
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
> http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>

	[[alternative HTML version deleted]]